INDEX

Explanations

numeric thresholds or limits

oai_token-act-pair · gpt-3.5-turbo

references to a specific limit or standard known as a threshold

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ulf

-0.74

ocate

-0.71

ocation

-0.70

orld

-0.68

ateur

-0.67

vironment

-0.67

oir

-0.66

iga

-0.66

ocated

-0.64

asca

-0.64

POSITIVE LOGITS

 thresholds

0.99

 threshold

0.92

 clearance

0.83

posts

0.77

 cutoff

0.77

witz

0.76

 heights

0.75

ansas

0.75

 crossings

0.72

=$

0.70

Activations Density 0.023%

numeric thresholds or limits

references to a specific limit or standard known as a threshold

No Comments

No Known Activations